© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45655
    Prev
    Next
    INDEX
    Explanations

    toxins/botox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tox
    -1.69
    TOX
    -0.82
    tol
    -0.56
    stattung
    -0.50
    isEmail
    -0.49
    ispiele
    -0.49
    ziehungen
    -0.48
     profissionais
    -0.48
    égias
    -0.48
    ğini
    -0.48
    POSITIVE LOGITS
    UnusedPrivate
    0.75
    CppMethod
    0.71
    WithIOException
    0.69
     EconPapers
    0.67
     cherchés
    0.64
    resave
    0.64
     дописавши
    0.63
    LookAnd
    0.60
    ️
    0.59
    WriteTagHelper
    0.57
    Activations Density 0.013%

    No Known Activations